Upload model

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "gemma-2b-it-qlora-amenokaku-code",
+  "architectures": [
+    "GemmaModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.0.dev0",
+  "unsloth_version": "2024.3",
+  "use_cache": true,
+  "vocab_size": 256000
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec8e6353d0bbc710c7c23e7968b4804c6ef6cc9ad21dbf2797f937b8b906111c
+size 4911634832

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a43e1fc6424e5bd06ed0baf4ddd7edff95d2394a41434b95f2be875dc917a94c
+size 4978829984

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03fde713e8c2f5dd05374dc29877bf60638d5cd3ce7e683f26b04431cd606172
+size 134242736

model.safetensors.index.json

@@ -0,0 +1,171 @@
+{
+  "metadata": {
+    "total_size": 10024689664
+  },
+  "weight_map": {
+    "embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.17.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.17.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.17.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.6.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.6.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.6.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.7.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.7.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "norm.weight": "model-00003-of-00003.safetensors"
+  }
+}